forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsvc.c
1797 lines (1545 loc) · 43.5 KB
/
svc.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/net/sunrpc/svc.c
*
* High-level RPC service routines
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*
* Multiple threads pools and NUMAisation
* Copyright (c) 2006 Silicon Graphics, Inc.
* by Greg Banks <gnb@melbourne.sgi.com>
*/
#include <linux/linkage.h>
#include <linux/sched/signal.h>
#include <linux/errno.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/bc_xprt.h>
#include <trace/events/sunrpc.h>
#include "fail.h"
#define RPCDBG_FACILITY RPCDBG_SVCDSP
static void svc_unregister(const struct svc_serv *serv, struct net *net);
#define SVC_POOL_DEFAULT SVC_POOL_GLOBAL
/*
* Mode for mapping cpus to pools.
*/
enum {
SVC_POOL_AUTO = -1, /* choose one of the others */
SVC_POOL_GLOBAL, /* no mapping, just a single global pool
* (legacy & UP mode) */
SVC_POOL_PERCPU, /* one pool per cpu */
SVC_POOL_PERNODE /* one pool per numa node */
};
/*
* Structure for mapping cpus to pools and vice versa.
* Setup once during sunrpc initialisation.
*/
struct svc_pool_map {
int count; /* How many svc_servs use us */
int mode; /* Note: int not enum to avoid
* warnings about "enumeration value
* not handled in switch" */
unsigned int npools;
unsigned int *pool_to; /* maps pool id to cpu or node */
unsigned int *to_pool; /* maps cpu or node to pool id */
};
static struct svc_pool_map svc_pool_map = {
.mode = SVC_POOL_DEFAULT
};
static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
static int
__param_set_pool_mode(const char *val, struct svc_pool_map *m)
{
int err, mode;
mutex_lock(&svc_pool_map_mutex);
err = 0;
if (!strncmp(val, "auto", 4))
mode = SVC_POOL_AUTO;
else if (!strncmp(val, "global", 6))
mode = SVC_POOL_GLOBAL;
else if (!strncmp(val, "percpu", 6))
mode = SVC_POOL_PERCPU;
else if (!strncmp(val, "pernode", 7))
mode = SVC_POOL_PERNODE;
else
err = -EINVAL;
if (err)
goto out;
if (m->count == 0)
m->mode = mode;
else if (mode != m->mode)
err = -EBUSY;
out:
mutex_unlock(&svc_pool_map_mutex);
return err;
}
static int
param_set_pool_mode(const char *val, const struct kernel_param *kp)
{
struct svc_pool_map *m = kp->arg;
return __param_set_pool_mode(val, m);
}
int sunrpc_set_pool_mode(const char *val)
{
return __param_set_pool_mode(val, &svc_pool_map);
}
EXPORT_SYMBOL(sunrpc_set_pool_mode);
/**
* sunrpc_get_pool_mode - get the current pool_mode for the host
* @buf: where to write the current pool_mode
* @size: size of @buf
*
* Grab the current pool_mode from the svc_pool_map and write
* the resulting string to @buf. Returns the number of characters
* written to @buf (a'la snprintf()).
*/
int
sunrpc_get_pool_mode(char *buf, size_t size)
{
struct svc_pool_map *m = &svc_pool_map;
switch (m->mode)
{
case SVC_POOL_AUTO:
return snprintf(buf, size, "auto");
case SVC_POOL_GLOBAL:
return snprintf(buf, size, "global");
case SVC_POOL_PERCPU:
return snprintf(buf, size, "percpu");
case SVC_POOL_PERNODE:
return snprintf(buf, size, "pernode");
default:
return snprintf(buf, size, "%d", m->mode);
}
}
EXPORT_SYMBOL(sunrpc_get_pool_mode);
static int
param_get_pool_mode(char *buf, const struct kernel_param *kp)
{
char str[16];
int len;
len = sunrpc_get_pool_mode(str, ARRAY_SIZE(str));
/* Ensure we have room for newline and NUL */
len = min_t(int, len, ARRAY_SIZE(str) - 2);
/* tack on the newline */
str[len] = '\n';
str[len + 1] = '\0';
return sysfs_emit(buf, str);
}
module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode,
&svc_pool_map, 0644);
/*
* Detect best pool mapping mode heuristically,
* according to the machine's topology.
*/
static int
svc_pool_map_choose_mode(void)
{
unsigned int node;
if (nr_online_nodes > 1) {
/*
* Actually have multiple NUMA nodes,
* so split pools on NUMA node boundaries
*/
return SVC_POOL_PERNODE;
}
node = first_online_node;
if (nr_cpus_node(node) > 2) {
/*
* Non-trivial SMP, or CONFIG_NUMA on
* non-NUMA hardware, e.g. with a generic
* x86_64 kernel on Xeons. In this case we
* want to divide the pools on cpu boundaries.
*/
return SVC_POOL_PERCPU;
}
/* default: one global pool */
return SVC_POOL_GLOBAL;
}
/*
* Allocate the to_pool[] and pool_to[] arrays.
* Returns 0 on success or an errno.
*/
static int
svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools)
{
m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
if (!m->to_pool)
goto fail;
m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
if (!m->pool_to)
goto fail_free;
return 0;
fail_free:
kfree(m->to_pool);
m->to_pool = NULL;
fail:
return -ENOMEM;
}
/*
* Initialise the pool map for SVC_POOL_PERCPU mode.
* Returns number of pools or <0 on error.
*/
static int
svc_pool_map_init_percpu(struct svc_pool_map *m)
{
unsigned int maxpools = nr_cpu_ids;
unsigned int pidx = 0;
unsigned int cpu;
int err;
err = svc_pool_map_alloc_arrays(m, maxpools);
if (err)
return err;
for_each_online_cpu(cpu) {
BUG_ON(pidx >= maxpools);
m->to_pool[cpu] = pidx;
m->pool_to[pidx] = cpu;
pidx++;
}
/* cpus brought online later all get mapped to pool0, sorry */
return pidx;
};
/*
* Initialise the pool map for SVC_POOL_PERNODE mode.
* Returns number of pools or <0 on error.
*/
static int
svc_pool_map_init_pernode(struct svc_pool_map *m)
{
unsigned int maxpools = nr_node_ids;
unsigned int pidx = 0;
unsigned int node;
int err;
err = svc_pool_map_alloc_arrays(m, maxpools);
if (err)
return err;
for_each_node_with_cpus(node) {
/* some architectures (e.g. SN2) have cpuless nodes */
BUG_ON(pidx > maxpools);
m->to_pool[node] = pidx;
m->pool_to[pidx] = node;
pidx++;
}
/* nodes brought online later all get mapped to pool0, sorry */
return pidx;
}
/*
* Add a reference to the global map of cpus to pools (and
* vice versa) if pools are in use.
* Initialise the map if we're the first user.
* Returns the number of pools. If this is '1', no reference
* was taken.
*/
static unsigned int
svc_pool_map_get(void)
{
struct svc_pool_map *m = &svc_pool_map;
int npools = -1;
mutex_lock(&svc_pool_map_mutex);
if (m->count++) {
mutex_unlock(&svc_pool_map_mutex);
return m->npools;
}
if (m->mode == SVC_POOL_AUTO)
m->mode = svc_pool_map_choose_mode();
switch (m->mode) {
case SVC_POOL_PERCPU:
npools = svc_pool_map_init_percpu(m);
break;
case SVC_POOL_PERNODE:
npools = svc_pool_map_init_pernode(m);
break;
}
if (npools <= 0) {
/* default, or memory allocation failure */
npools = 1;
m->mode = SVC_POOL_GLOBAL;
}
m->npools = npools;
mutex_unlock(&svc_pool_map_mutex);
return npools;
}
/*
* Drop a reference to the global map of cpus to pools.
* When the last reference is dropped, the map data is
* freed; this allows the sysadmin to change the pool.
*/
static void
svc_pool_map_put(void)
{
struct svc_pool_map *m = &svc_pool_map;
mutex_lock(&svc_pool_map_mutex);
if (!--m->count) {
kfree(m->to_pool);
m->to_pool = NULL;
kfree(m->pool_to);
m->pool_to = NULL;
m->npools = 0;
}
mutex_unlock(&svc_pool_map_mutex);
}
static int svc_pool_map_get_node(unsigned int pidx)
{
const struct svc_pool_map *m = &svc_pool_map;
if (m->count) {
if (m->mode == SVC_POOL_PERCPU)
return cpu_to_node(m->pool_to[pidx]);
if (m->mode == SVC_POOL_PERNODE)
return m->pool_to[pidx];
}
return NUMA_NO_NODE;
}
/*
* Set the given thread's cpus_allowed mask so that it
* will only run on cpus in the given pool.
*/
static inline void
svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
{
struct svc_pool_map *m = &svc_pool_map;
unsigned int node = m->pool_to[pidx];
/*
* The caller checks for sv_nrpools > 1, which
* implies that we've been initialized.
*/
WARN_ON_ONCE(m->count == 0);
if (m->count == 0)
return;
switch (m->mode) {
case SVC_POOL_PERCPU:
{
set_cpus_allowed_ptr(task, cpumask_of(node));
break;
}
case SVC_POOL_PERNODE:
{
set_cpus_allowed_ptr(task, cpumask_of_node(node));
break;
}
}
}
/**
* svc_pool_for_cpu - Select pool to run a thread on this cpu
* @serv: An RPC service
*
* Use the active CPU and the svc_pool_map's mode setting to
* select the svc thread pool to use. Once initialized, the
* svc_pool_map does not change.
*
* Return value:
* A pointer to an svc_pool
*/
struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv)
{
struct svc_pool_map *m = &svc_pool_map;
int cpu = raw_smp_processor_id();
unsigned int pidx = 0;
if (serv->sv_nrpools <= 1)
return serv->sv_pools;
switch (m->mode) {
case SVC_POOL_PERCPU:
pidx = m->to_pool[cpu];
break;
case SVC_POOL_PERNODE:
pidx = m->to_pool[cpu_to_node(cpu)];
break;
}
return &serv->sv_pools[pidx % serv->sv_nrpools];
}
int svc_rpcb_setup(struct svc_serv *serv, struct net *net)
{
int err;
err = rpcb_create_local(net);
if (err)
return err;
/* Remove any stale portmap registrations */
svc_unregister(serv, net);
return 0;
}
EXPORT_SYMBOL_GPL(svc_rpcb_setup);
void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net)
{
svc_unregister(serv, net);
rpcb_put_local(net);
}
EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
static int svc_uses_rpcbind(struct svc_serv *serv)
{
struct svc_program *progp;
unsigned int i;
for (progp = serv->sv_program; progp; progp = progp->pg_next) {
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
if (!progp->pg_vers[i]->vs_hidden)
return 1;
}
}
return 0;
}
int svc_bind(struct svc_serv *serv, struct net *net)
{
if (!svc_uses_rpcbind(serv))
return 0;
return svc_rpcb_setup(serv, net);
}
EXPORT_SYMBOL_GPL(svc_bind);
#if defined(CONFIG_SUNRPC_BACKCHANNEL)
static void
__svc_init_bc(struct svc_serv *serv)
{
lwq_init(&serv->sv_cb_list);
}
#else
static void
__svc_init_bc(struct svc_serv *serv)
{
}
#endif
/*
* Create an RPC service
*/
static struct svc_serv *
__svc_create(struct svc_program *prog, struct svc_stat *stats,
unsigned int bufsize, int npools, int (*threadfn)(void *data))
{
struct svc_serv *serv;
unsigned int vers;
unsigned int xdrsize;
unsigned int i;
if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
return NULL;
serv->sv_name = prog->pg_name;
serv->sv_program = prog;
serv->sv_stats = stats;
if (bufsize > RPCSVC_MAXPAYLOAD)
bufsize = RPCSVC_MAXPAYLOAD;
serv->sv_max_payload = bufsize? bufsize : 4096;
serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE);
serv->sv_threadfn = threadfn;
xdrsize = 0;
while (prog) {
prog->pg_lovers = prog->pg_nvers-1;
for (vers=0; vers<prog->pg_nvers ; vers++)
if (prog->pg_vers[vers]) {
prog->pg_hivers = vers;
if (prog->pg_lovers > vers)
prog->pg_lovers = vers;
if (prog->pg_vers[vers]->vs_xdrsize > xdrsize)
xdrsize = prog->pg_vers[vers]->vs_xdrsize;
}
prog = prog->pg_next;
}
serv->sv_xdrsize = xdrsize;
INIT_LIST_HEAD(&serv->sv_tempsocks);
INIT_LIST_HEAD(&serv->sv_permsocks);
timer_setup(&serv->sv_temptimer, NULL, 0);
spin_lock_init(&serv->sv_lock);
__svc_init_bc(serv);
serv->sv_nrpools = npools;
serv->sv_pools =
kcalloc(serv->sv_nrpools, sizeof(struct svc_pool),
GFP_KERNEL);
if (!serv->sv_pools) {
kfree(serv);
return NULL;
}
for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_pool *pool = &serv->sv_pools[i];
dprintk("svc: initialising pool %u for %s\n",
i, serv->sv_name);
pool->sp_id = i;
lwq_init(&pool->sp_xprts);
INIT_LIST_HEAD(&pool->sp_all_threads);
init_llist_head(&pool->sp_idle_threads);
percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL);
percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL);
}
return serv;
}
/**
* svc_create - Create an RPC service
* @prog: the RPC program the new service will handle
* @bufsize: maximum message size for @prog
* @threadfn: a function to service RPC requests for @prog
*
* Returns an instantiated struct svc_serv object or NULL.
*/
struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize,
int (*threadfn)(void *data))
{
return __svc_create(prog, NULL, bufsize, 1, threadfn);
}
EXPORT_SYMBOL_GPL(svc_create);
/**
* svc_create_pooled - Create an RPC service with pooled threads
* @prog: the RPC program the new service will handle
* @stats: the stats struct if desired
* @bufsize: maximum message size for @prog
* @threadfn: a function to service RPC requests for @prog
*
* Returns an instantiated struct svc_serv object or NULL.
*/
struct svc_serv *svc_create_pooled(struct svc_program *prog,
struct svc_stat *stats,
unsigned int bufsize,
int (*threadfn)(void *data))
{
struct svc_serv *serv;
unsigned int npools = svc_pool_map_get();
serv = __svc_create(prog, stats, bufsize, npools, threadfn);
if (!serv)
goto out_err;
serv->sv_is_pooled = true;
return serv;
out_err:
svc_pool_map_put();
return NULL;
}
EXPORT_SYMBOL_GPL(svc_create_pooled);
/*
* Destroy an RPC service. Should be called with appropriate locking to
* protect sv_permsocks and sv_tempsocks.
*/
void
svc_destroy(struct svc_serv **servp)
{
struct svc_serv *serv = *servp;
unsigned int i;
*servp = NULL;
dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name);
timer_shutdown_sync(&serv->sv_temptimer);
/*
* Remaining transports at this point are not expected.
*/
WARN_ONCE(!list_empty(&serv->sv_permsocks),
"SVC: permsocks remain for %s\n", serv->sv_program->pg_name);
WARN_ONCE(!list_empty(&serv->sv_tempsocks),
"SVC: tempsocks remain for %s\n", serv->sv_program->pg_name);
cache_clean_deferred(serv);
if (serv->sv_is_pooled)
svc_pool_map_put();
for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_pool *pool = &serv->sv_pools[i];
percpu_counter_destroy(&pool->sp_messages_arrived);
percpu_counter_destroy(&pool->sp_sockets_queued);
percpu_counter_destroy(&pool->sp_threads_woken);
}
kfree(serv->sv_pools);
kfree(serv);
}
EXPORT_SYMBOL_GPL(svc_destroy);
static bool
svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
{
unsigned long pages, ret;
/* bc_xprt uses fore channel allocated buffers */
if (svc_is_backchannel(rqstp))
return true;
pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply.
* We assume one is at most one page
*/
WARN_ON_ONCE(pages > RPCSVC_MAXPAGES);
if (pages > RPCSVC_MAXPAGES)
pages = RPCSVC_MAXPAGES;
ret = alloc_pages_bulk_array_node(GFP_KERNEL, node, pages,
rqstp->rq_pages);
return ret == pages;
}
/*
* Release an RPC server buffer
*/
static void
svc_release_buffer(struct svc_rqst *rqstp)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++)
if (rqstp->rq_pages[i])
put_page(rqstp->rq_pages[i]);
}
struct svc_rqst *
svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
{
struct svc_rqst *rqstp;
rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node);
if (!rqstp)
return rqstp;
folio_batch_init(&rqstp->rq_fbatch);
rqstp->rq_server = serv;
rqstp->rq_pool = pool;
rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0);
if (!rqstp->rq_scratch_page)
goto out_enomem;
rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
if (!rqstp->rq_argp)
goto out_enomem;
rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
if (!rqstp->rq_resp)
goto out_enomem;
if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node))
goto out_enomem;
return rqstp;
out_enomem:
svc_rqst_free(rqstp);
return NULL;
}
EXPORT_SYMBOL_GPL(svc_rqst_alloc);
static struct svc_rqst *
svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
{
struct svc_rqst *rqstp;
rqstp = svc_rqst_alloc(serv, pool, node);
if (!rqstp)
return ERR_PTR(-ENOMEM);
spin_lock_bh(&serv->sv_lock);
serv->sv_nrthreads += 1;
spin_unlock_bh(&serv->sv_lock);
atomic_inc(&pool->sp_nrthreads);
/* Protected by whatever lock the service uses when calling
* svc_set_num_threads()
*/
list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
return rqstp;
}
/**
* svc_pool_wake_idle_thread - Awaken an idle thread in @pool
* @pool: service thread pool
*
* Can be called from soft IRQ or process context. Finding an idle
* service thread and marking it BUSY is atomic with respect to
* other calls to svc_pool_wake_idle_thread().
*
*/
void svc_pool_wake_idle_thread(struct svc_pool *pool)
{
struct svc_rqst *rqstp;
struct llist_node *ln;
rcu_read_lock();
ln = READ_ONCE(pool->sp_idle_threads.first);
if (ln) {
rqstp = llist_entry(ln, struct svc_rqst, rq_idle);
WRITE_ONCE(rqstp->rq_qtime, ktime_get());
if (!task_is_running(rqstp->rq_task)) {
wake_up_process(rqstp->rq_task);
trace_svc_wake_up(rqstp->rq_task->pid);
percpu_counter_inc(&pool->sp_threads_woken);
}
rcu_read_unlock();
return;
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(svc_pool_wake_idle_thread);
static struct svc_pool *
svc_pool_next(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
return pool ? pool : &serv->sv_pools[(*state)++ % serv->sv_nrpools];
}
static struct svc_pool *
svc_pool_victim(struct svc_serv *serv, struct svc_pool *target_pool,
unsigned int *state)
{
struct svc_pool *pool;
unsigned int i;
retry:
pool = target_pool;
if (pool != NULL) {
if (atomic_inc_not_zero(&pool->sp_nrthreads))
goto found_pool;
return NULL;
} else {
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
if (atomic_inc_not_zero(&pool->sp_nrthreads))
goto found_pool;
}
return NULL;
}
found_pool:
set_bit(SP_VICTIM_REMAINS, &pool->sp_flags);
set_bit(SP_NEED_VICTIM, &pool->sp_flags);
if (!atomic_dec_and_test(&pool->sp_nrthreads))
return pool;
/* Nothing left in this pool any more */
clear_bit(SP_NEED_VICTIM, &pool->sp_flags);
clear_bit(SP_VICTIM_REMAINS, &pool->sp_flags);
goto retry;
}
static int
svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
struct svc_rqst *rqstp;
struct task_struct *task;
struct svc_pool *chosen_pool;
unsigned int state = serv->sv_nrthreads-1;
int node;
do {
nrservs--;
chosen_pool = svc_pool_next(serv, pool, &state);
node = svc_pool_map_get_node(chosen_pool->sp_id);
rqstp = svc_prepare_thread(serv, chosen_pool, node);
if (IS_ERR(rqstp))
return PTR_ERR(rqstp);
task = kthread_create_on_node(serv->sv_threadfn, rqstp,
node, "%s", serv->sv_name);
if (IS_ERR(task)) {
svc_exit_thread(rqstp);
return PTR_ERR(task);
}
rqstp->rq_task = task;
if (serv->sv_nrpools > 1)
svc_pool_map_set_cpumask(task, chosen_pool->sp_id);
svc_sock_update_bufs(serv);
wake_up_process(task);
} while (nrservs > 0);
return 0;
}
static int
svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
unsigned int state = serv->sv_nrthreads-1;
struct svc_pool *victim;
do {
victim = svc_pool_victim(serv, pool, &state);
if (!victim)
break;
svc_pool_wake_idle_thread(victim);
wait_on_bit(&victim->sp_flags, SP_VICTIM_REMAINS,
TASK_IDLE);
nrservs++;
} while (nrservs < 0);
return 0;
}
/**
* svc_set_num_threads - adjust number of threads per RPC service
* @serv: RPC service to adjust
* @pool: Specific pool from which to choose threads, or NULL
* @nrservs: New number of threads for @serv (0 or less means kill all threads)
*
* Create or destroy threads to make the number of threads for @serv the
* given number. If @pool is non-NULL, change only threads in that pool;
* otherwise, round-robin between all pools for @serv. @serv's
* sv_nrthreads is adjusted for each thread created or destroyed.
*
* Caller must ensure mutual exclusion between this and server startup or
* shutdown.
*
* Returns zero on success or a negative errno if an error occurred while
* starting a thread.
*/
int
svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
if (!pool)
nrservs -= serv->sv_nrthreads;
else
nrservs -= atomic_read(&pool->sp_nrthreads);
if (nrservs > 0)
return svc_start_kthreads(serv, pool, nrservs);
if (nrservs < 0)
return svc_stop_kthreads(serv, pool, nrservs);
return 0;
}
EXPORT_SYMBOL_GPL(svc_set_num_threads);
/**
* svc_rqst_replace_page - Replace one page in rq_pages[]
* @rqstp: svc_rqst with pages to replace
* @page: replacement page
*
* When replacing a page in rq_pages, batch the release of the
* replaced pages to avoid hammering the page allocator.
*
* Return values:
* %true: page replaced
* %false: array bounds checking failed
*/
bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page)
{
struct page **begin = rqstp->rq_pages;
struct page **end = &rqstp->rq_pages[RPCSVC_MAXPAGES];
if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) {
trace_svc_replace_page_err(rqstp);
return false;
}
if (*rqstp->rq_next_page) {
if (!folio_batch_add(&rqstp->rq_fbatch,
page_folio(*rqstp->rq_next_page)))
__folio_batch_release(&rqstp->rq_fbatch);
}
get_page(page);
*(rqstp->rq_next_page++) = page;
return true;
}
EXPORT_SYMBOL_GPL(svc_rqst_replace_page);
/**
* svc_rqst_release_pages - Release Reply buffer pages
* @rqstp: RPC transaction context
*
* Release response pages that might still be in flight after
* svc_send, and any spliced filesystem-owned pages.
*/
void svc_rqst_release_pages(struct svc_rqst *rqstp)
{
int i, count = rqstp->rq_next_page - rqstp->rq_respages;
if (count) {
release_pages(rqstp->rq_respages, count);
for (i = 0; i < count; i++)
rqstp->rq_respages[i] = NULL;
}
}
/*
* Called from a server thread as it's exiting. Caller must hold the "service
* mutex" for the service.
*/
void
svc_rqst_free(struct svc_rqst *rqstp)
{
folio_batch_release(&rqstp->rq_fbatch);
svc_release_buffer(rqstp);
if (rqstp->rq_scratch_page)
put_page(rqstp->rq_scratch_page);
kfree(rqstp->rq_resp);
kfree(rqstp->rq_argp);
kfree(rqstp->rq_auth_data);
kfree_rcu(rqstp, rq_rcu_head);
}
EXPORT_SYMBOL_GPL(svc_rqst_free);
void
svc_exit_thread(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct svc_pool *pool = rqstp->rq_pool;
list_del_rcu(&rqstp->rq_all);
atomic_dec(&pool->sp_nrthreads);
spin_lock_bh(&serv->sv_lock);
serv->sv_nrthreads -= 1;
spin_unlock_bh(&serv->sv_lock);
svc_sock_update_bufs(serv);
svc_rqst_free(rqstp);
clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags);
}
EXPORT_SYMBOL_GPL(svc_exit_thread);
/*
* Register an "inet" protocol family netid with the local
* rpcbind daemon via an rpcbind v4 SET request.
*
* No netconfig infrastructure is available in the kernel, so
* we map IP_ protocol numbers to netids by hand.
*
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
static int __svc_rpcb_register4(struct net *net, const u32 program,
const u32 version,
const unsigned short protocol,
const unsigned short port)
{
const struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
const char *netid;
int error;
switch (protocol) {
case IPPROTO_UDP:
netid = RPCBIND_NETID_UDP;